Assessing risk of nodal metastasis and relapse-free survival by CP-GEP (Merlin™ Test) in a single-center retrospective case series of stage pT1a-4b cN0M0 melanoma patients

hair genotype showed significantly lower automated nevus counts compared to other variants (p <0.001) (Fig 2).Limitations include retrospective nature, single-center, and lack of generalizability.Figure 1.Automated 3-dimensional total body lesion segmentation provided by machine learning algorithms.Figure 2. Association between machine learning outcomes from 3-dimensional total body photography maps and different MC1R genotypes.P-values shown take into consideration automated nevus counts.Total lesion counts among groups showed no significant differences (Kruskal-Wallis, p = 0.84).Conclusions: Machine learning applications in 3-dimensional total body photography can provide an automated description of patients' skin characteristics, which correlate with phenotypic traits that are associated with an increased risk of developing melanoma.These tools could enhance identification of patients at higher melanoma risk.